Improving the Automated Detection of Silent AF Episodes Based on HR Variability Measures
Atrial fibrillation (AF) is one of the most common types of heart arrhythmias and it leads to increased risk of stroke and heart attack. We proposed improved method for automated AF detection with additional aggregation of short AF episodes to provide more reliable information on risk for the patient. The aggregation parameters underwent optimization process and evaluation study has been carried out with a use of two databases provided by PhysioNet.org. Final results showed that the new method for automated detection of AF episodes was capable to detect more than 96% of all reference AF provided by the MIT-BIH Atrial Fibrillation Database, and above 93% for the Long-Term AF Database. At the same time less than 7% of the detected AF were false episodes for both databases. The proposed method can be easily implemented in the mobile instrumentation for long-term monitoring where the computational power is usually limited.
KeywordsAtrial fibrillation Automated AF detection Heart rate variability measures
This scientific research work is supported by The National Centre for Research and Development of Poland (grant No. STRATEGMED2/269343/18/NCBR/2016).
- 10.Roj, D., Wrobel, J., Matonia, A., Sobotnicka, E.: Hardware design issues and functional requirements for smart wristband monitor of silent atrial fibrillation. In: Proceedings of 24th International Conference on Mixed Design of Integrated Circuits and Systems MIXDES 2017, Bydgoszcz, 22–24 June, pp. 596–600 (2017)Google Scholar
- 19.Ghodrati, A., Murray, B., Marinello, S.: RR interval analysis for detection of Atrial Fibrillation in ECG monitors. In: 30th Annual International Conference of the IEEE EMBS, pp. 601–604 (2008). http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=4649224
- 20.Logan, B., Healey, J.: Robust detection of atrial fibrillation for a long term telemonitoring system. In: Computers in Cardiology, pp. 619–622. IEEE (2005). http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=1588177
- 22.Cerutti, S., Mainardi, L.T., Porta, A., Bianchi, A.M.: Analysis of the dynamics of RR interval series for the detection of atrial fibrillation episodes. In: Computers in Cardiology, pp. 77–80. IEEE (1997). http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=647834
- 25.Petrucci, E., Balian, V., Filippini, G., Mainardi, L.T.: Atrial fibrillation detection algorithms for very long term ECG monitoring. In: Computers in Cardiology, pp. 623–626. IEEE (2005). http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=1588178
- 26.Artis, S.G., Mark, R., Moody, G.: Detection of atrial fibrillation using artificial neural networks. In: Computers in Cardiology, pp. 173–176. IEEE (1991)Google Scholar
- 27.Henzel, N., Wrobel, J., Horoba, K.: Atrial fibrillation episodes detection based on classification of heart rate derived features. In: Proceedings of 24th International Conference on Mixed Design of Integrated Circuits and Systems, MIXDES 2017, Bydgoszcz, 22–24 June, pp. 571–576 (2017)Google Scholar
- 28.Roj, D., Wrobel, J., Matonia, A., Horoba, K., Henzel, N.: Control and signal processing software embedded in smart wristband monitor of silent atrial fibrillation. In: Proceedings of 24th International Conference on Mixed Design of Integrated Circuits and Systems, MIXDES 2017, Bydgoszcz, 22–24 June, pp. 585–590 (2017)Google Scholar
- 30.Moody, G.B., Mark, R.G., et al.: A new method for detecting atrial fibrillation using R-R intervals. Comput. Cardiol. 10, 227–230 (1983)Google Scholar